# Boson

## Docs

- [Create speech](https://docs.boson.ai/api-reference/text-to-speech/create-speech.md): Generate speech audio from text. Returns an audio file, or a stream of raw PCM chunks when `stream` is `true`.
- [Create voice](https://docs.boson.ai/api-reference/voices/create-voice.md): Register a reusable reference voice for cloning. Identical audio re-registered under the same API key returns the existing voice. Pass the returned `voice` ID to the `voice` field of `POST /v1/audio/speech` instead of sending `ref_audio` on every request.
- [Get voice](https://docs.boson.ai/api-reference/voices/get-voice.md): Fetch a single reference voice by ID.
- [List voices](https://docs.boson.ai/api-reference/voices/list-voices.md): List the reference voices registered under your API key.
- [Authentication](https://docs.boson.ai/authentication.md): Authenticate Boson API requests with a Bearer token.
- [Higgs Audio v3 Instruct](https://docs.boson.ai/models/higgs-audio-instruct/overview.md): Audio-in LLM with voice-agent reflexes: understands speech and text, follows instructions, calls tools, handles interruptions, and responds with intelligent text output.
- [Languages](https://docs.boson.ai/models/higgs-audio-tts/languages.md): Higgs Audio TTS supports 100 languages with single-digit WER/CER.
- [Higgs Audio v3 TTS](https://docs.boson.ai/models/higgs-audio-tts/overview.md): Chat-native text-to-speech with streaming, 100 languages, instant voice cloning, and inline emotion and style control.
- [Tags](https://docs.boson.ai/models/higgs-audio-tts/tags.md): Inline control tokens that shape emotion, style, prosody, and sound effects inside the input text.
- [Voices](https://docs.boson.ai/models/higgs-audio-tts/voices.md): Use preset voices, reference audio, or reusable custom voices with Higgs Audio TTS.
- [Higgs Avatar v1](https://docs.boson.ai/models/higgs-avatar/overview.md): Real-time avatar video generation from a single still image and a driving voice, with lip sync, head motion, and expression aligned to audio.
- [Welcome to Boson AI](https://docs.boson.ai/overview.md): Build real-time voice and multimodal AI agents for natural, responsive conversations.

## OpenAPI Specs

- [openapi](https://docs.boson.ai/openapi.json)